diff --git a/spec/canonical.sx b/spec/canonical.sx new file mode 100644 index 00000000..36540b10 --- /dev/null +++ b/spec/canonical.sx @@ -0,0 +1,117 @@ +(define + canonical-serialize + :effects () + (fn + (val) + (case + (type-of val) + "nil" + "nil" + "boolean" + (if val "true" "false") + "number" + (canonical-number val) + "string" + (str "\"" (escape-string val) "\"") + "symbol" + (symbol-name val) + "keyword" + (str ":" (keyword-name val)) + "list" + (str "(" (join " " (map canonical-serialize val)) ")") + "dict" + (canonical-dict val) + :else (str val)))) + +(define + canonical-number + :effects () + (fn + (n) + (let + ((s (str n))) + (if + (ends-with? s ".0") + (slice s 0 (- (len s) 2)) + (if + (contains-char? s ".") + (let + ((trimmed (trim-right s "0"))) + (if (ends-with? trimmed ".") (str trimmed "0") trimmed)) + s))))) + +(define + canonical-dict + :effects () + (fn + (d) + (let + ((sorted-keys (sort (keys d)))) + (str + "{" + (join + " " + (reduce + (fn + (acc key) + (concat + acc + (list (str ":" key) (canonical-serialize (dict-get d key))))) + (list) + sorted-keys)) + "}")))) + +(define + content-id + :effects () + (fn (expr) (sha3-256 (canonical-serialize expr)))) + +(define + content-id-short + :effects () + (fn (expr) (slice (content-id expr) 0 16))) + +(define + make-bytecode-module + :effects () + (fn + (version source-hash code) + (list (quote sxbc) version source-hash code))) + +(define + bytecode-module? + :effects () + (fn + (expr) + (and (list? expr) (>= (len expr) 4) (= (first expr) (quote sxbc))))) + +(define bytecode-module-version :effects () (fn (m) (nth m 1))) + +(define bytecode-module-source-hash :effects () (fn (m) (nth m 2))) + +(define bytecode-module-code :effects () (fn (m) (nth m 3))) + +(define + make-code-object + :effects () + (fn + (arity upvalue-count bytecode constants) + (let + ((parts (list (quote code)))) + (when (> arity 0) (set! parts (concat parts (list :arity arity)))) + (when + (> upvalue-count 0) + (set! parts (concat parts (list :upvalue-count upvalue-count)))) + (concat parts (list :bytecode bytecode :constants constants))))) + +(define + make-provenance + :effects () + (fn + (source-cid bytecode-cid compiler-cid timestamp) + (list + (quote provenance) + :source-cid source-cid + :bytecode-cid bytecode-cid + :compiler-cid compiler-cid + :timestamp timestamp))) diff --git a/spec/tests/test-canonical.sx b/spec/tests/test-canonical.sx new file mode 100644 index 00000000..7022ba29 --- /dev/null +++ b/spec/tests/test-canonical.sx @@ -0,0 +1,91 @@ +(test-group + "canonical-serialize" + (test "nil" (assert= (canonical-serialize nil) "nil")) + (test + "booleans" + (assert= (canonical-serialize true) "true") + (assert= (canonical-serialize false) "false")) + (test + "integers" + (assert= (canonical-serialize 0) "0") + (assert= (canonical-serialize 42) "42") + (assert= (canonical-serialize -7) "-7")) + (test + "strings" + (assert= (canonical-serialize "hello") "\"hello\"") + (assert= (canonical-serialize "") "\"\"") + (assert= (canonical-serialize "a\"b") "\"a\\\"b\"")) + (test + "symbols" + (assert= (canonical-serialize (quote deref)) "deref") + (assert= (canonical-serialize (quote swap!)) "swap!")) + (test + "keywords" + (assert= (canonical-serialize :class) ":class") + (assert= (canonical-serialize :arity) ":arity")) + (test "empty list" (assert= (canonical-serialize (list)) "()")) + (test "flat list" (assert= (canonical-serialize (list 1 2 3)) "(1 2 3)")) + (test + "nested list" + (assert= + (canonical-serialize + (list (quote div) :class "flex" (list (quote h2) "title"))) + "(div :class \"flex\" (h2 \"title\"))")) + (test + "dict keys sorted" + (let + ((d (dict "zebra" 1 "alpha" 2 "middle" 3))) + (assert= (canonical-serialize d) "{:alpha 2 :middle 3 :zebra 1}"))) + (test + "dict with nested values" + (let + ((d (dict "a" (list 1 2) "b" "hello"))) + (assert= (canonical-serialize d) "{:a (1 2) :b \"hello\"}")))) + +(test-group + "content-id" + (test + "same expression same CID" + (assert= (content-id (list 1 2 3)) (content-id (list 1 2 3)))) + (test + "different expression different CID" + (assert + (not (= (content-id (list 1 2 3)) (content-id (list 1 2 4)))))) + (test + "CID is a hex string" + (let + ((cid (content-id 42))) + (assert (string? cid)) + (assert= (len cid) 64))) + (test + "short CID is 16 chars" + (let ((cid (content-id-short 42))) (assert= (len cid) 16))) + (test + "short CID is prefix of full CID" + (let + ((full (content-id 42)) (short (content-id-short 42))) + (assert= short (slice full 0 16))))) + +(test-group + "bytecode-module" + (test + "make and query" + (let + ((m (make-bytecode-module 1 "abc123" (list (quote code) :bytecode (list 1 2 3))))) + (assert (bytecode-module? m)) + (assert= (bytecode-module-version m) 1) + (assert= (bytecode-module-source-hash m) "abc123"))) + (test + "non-module fails predicate" + (assert (not (bytecode-module? (list 1 2 3)))) + (assert (not (bytecode-module? "hello"))))) + +(test-group + "provenance" + (test + "make provenance record" + (let + ((p (make-provenance "src-cid" "bc-cid" "compiler-cid" "2026-03-27T00:00:00Z"))) + (assert= (first p) (quote provenance)) + (assert= (nth p 2) "src-cid") + (assert= (nth p 4) "bc-cid"))))